Dynamic Parameter Identification of Robots Using a Neural Net

dc.contributor.author	Jiang, Zhao-Hui
dc.date.accessioned	2017-11-16T13:37:59Z
dc.date.available	2017-11-16T13:37:59Z
dc.date.issued	2009
dc.identifier.issn	1224-5615
dc.identifier.uri	http://10.11.10.50/xmlui/handle/123456789/4888
dc.description	The Annals of ''Dunarea de Jos'' University of Galati : Fascicle XIV MECHANICAL ENGINEERING, ISSN 1224 - 5615	ro_RO
dc.description.abstract	This paper addresses issues of dynamic parameter identification of robot manipulators. A new identification approach with neural network based compensation of uncertain dynamics is proposed. The parameter identification process is divided into two steps. The first step is to determine unknown dynamic parameters using inverse dynamics of the robot manipulator and pseudo-inverse matrices. The second step is to establish a dynamic compensator by neural network and learning method for improving accuracy of the dynamic model with parameters given in the first step. A Direct Drive (DD) SCARA type industrial robot arm AdeptOne is used as an application example for the parameter identification. Simulations and experiments are carried out. Comparison of the results confirms the correctness and usefulness of the proposed identification method.	ro_RO
dc.language.iso	en	ro_RO
dc.publisher	Universitatea "Dunărea de Jos" din Galați	ro_RO
dc.subject	robot manipulator	ro_RO
dc.subject	neural network	ro_RO
dc.subject	identification	ro_RO
dc.title	Dynamic Parameter Identification of Robots Using a Neural Net	ro_RO
dc.type	Article	ro_RO